Due to the problem of insufficient dynamic human ear data, the Changchun University dynamic human ear (CCU-DE) database, which is a small sample human ear database, was developed in this study. The database fully considers the various complex situations and posture changes of human ear images, such as translation angle, rotation angle, illumination change, occlusion and interference, etc., making the research of dynamic human ear recognition closer to complex real-life situations, and increasing the applicability of human ear dynamic recognition. In order to test the practicability and effectiveness of the developed CCU-DE small sample database, we designed a dynamic human ear recognition system block diagram based on a deep learning model, which was pre-trained by a migration learning method. Aiming at multi-posture changes under different contrasts, translation and rotation motions, and with or without occlusion, simulation studies were conducted using the CCU-DE small sample database and different deep learning models, such as YOLOv3, YOLOv4, YOLOv5, Faster R-CNN, and SSD. The experimental results showed that the CCU-DE database can be well used for dynamic ear recognition, and it can be tested by using different deep learning models with higher test accuracy.
To improve the precision and sensitivity of the detection in near infrared gas detection system, the selection of light source and design of gas chamber structure are two key links. In this paper, the near infrared (NIR) light sources fabricated with PbSe quantum dots (QDs) and a new gas cell structure using an ellipsoid reflector were designed to test the concentration of methane (CH4). The double wavelengths differential detection method was used in the paper. The signal wavelength is 1.665 μm from the NIR QD-based light source with 5.1 nm PbSe QDs. The reference wavelength is 1.943 μm from the NIR QD-based light source with 6.1 nm PbSe QDs. The experimental results show that the differential gain signal could be enhanced 80 times when the major axis, the focus, and the open length of the ellipsoid reflector are 4.18 cm, 3.98 cm, and 0.36 cm, respectively. The structure will be convenient for the signal amplifying, AD converting, and other process in the latter circuits, and therefore both the detection sensitivity and precision can be improved.
The data acquisition (DAQ) system was developed by studying and using DAQmx driver based on virtual instrument in this paper. The system can realize temperature and voltage signal acquisition and processing. Temperature acquisition took K type thermocouple sensor, the high-accuracy thermocouple measurements module NI SCXI-1102 and high-speed data acquisition module NI PXI-6251. Voltage acquisition took highspeed data acquisition module NI PXI-6289 and DM1661 noise generation. LabVIEW8.6 software is adopted as the development platform. The simulation results show that hardware configuration reasonable and the interface is beautiful and easy to operate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.